How to Use the Milvus (Open-Source Vector Database) MCP in Vercel AI SDK

Q: How do I perform an ANN search using Milvus (Open-Source Vector Database) in Vercel AI SDK?

You pass your vector array to the searchvectors tool within your streamText call. The AI client then handles the response stream, displaying the nearest neighbors as the data returns from the server.

Q: Can I filter data in Milvus (Open-Source Vector Database) while using Vercel AI SDK?

Yes, you use the queryentities tool for scalar filtering. This lets your agent narrow down results before performing further logic.

Q: Does Milvus (Open-Source Vector Database) support real-time updates in Vercel AI SDK?

The server provides deleteentities to manage your data state immediately. You can trigger these deletions through your agent to keep your indices clean.

Q: How do I check my Milvus (Open-Source Vector Database) status?

Run getcollectionstats via your MCP client. It provides the current row counts so you know your database is ready for queries.

Stream vector search results directly into your Vercel AI SDK interface for real-time data visibility.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Milvus (Open-Source Vector Database) MCP to Vercel AI SDK

Create your Vinkius account to connect Milvus (Open-Source Vector Database) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Milvus (Open-Source Vector Database) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Vector Search for AI SDK

Feed your embedding inputs into `search_vectors` to retrieve nearest neighbors directly within your streaming response flow. Your frontend renders the results as they arrive, cutting out the typical wait for backend processing. This setup keeps your UI responsive while the AI client processes high-dimensional data. You define the dimension array, and the server returns the matches instantly.

Collection Auditing with AI SDK

Call `list_collections` and `describe_collection` to verify your schema state before running intensive queries. You’ll see the exact structure of your Milvus indices without leaving your code editor. Use `get_collection_stats` to monitor row counts and index health. This prevents your Edge Functions from timing out on empty or malformed collections.

Targeted Entity Retrieval for AI SDK

Extract specific records using `get_entities` by passing known primary keys to your AI agent. This allows you to pull exact context for user-facing displays without broad scans. Use `query_entities` when you need to filter by scalar fields. It gives you precise control over exactly what data enters the stream.

Setup guide

Set up Milvus (Open-Source Vector Database) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Milvus (Open-Source Vector Database) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Milvus (Open-Source Vector Database) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Milvus. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Milvus (Open-Source Vector Database) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Milvus (Open-Source Vector Database) MCP in Vercel AI SDK

You pass your vector array to the `search_vectors` tool within your `streamText` call. The AI client then handles the response stream, displaying the nearest neighbors as the data returns from the server.

Yes, you use the `query_entities` tool for scalar filtering. This lets your agent narrow down results before performing further logic.

The server provides `delete_entities` to manage your data state immediately. You can trigger these deletions through your agent to keep your indices clean.

Run `get_collection_stats` via your MCP client. It provides the current row counts so you know your database is ready for queries.

Your data remains in your infrastructure. This MCP server acts as a bridge, only passing the specific vector records you request through the secure connection.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript